数据指标波动假设检验统计

eda/recommended_indexs/hypothesis_test.py

+#! -*- coding: utf8 -*-
+import pandas as pd
+from scipy.stats import ttest_ind
+from scipy.stats import levene
+import pymysql
+import datetime
+from utils import con_sql
+
+#########推荐策略前后统计指标假设检验（t检验）###############
+
+#自动获取昨日日期
+def get_yesterday_date():
+	#自动获取昨天的日期,如"2018-08-08"
+	"""
+	:rtype : str
+	"""
+	today = datetime.date.today()
+	yesterday = today - datetime.timedelta(days=1)
+	yesterday = yesterday.strftime("%Y-%m-%d")
+	return yesterday
+yesterday=get_yesterday_date
+#自动获取10日前的日期
+def get_somedate():
+	#自动获取10日前的日期,如"2018-07-28"
+	"""
+	:rtype : str
+	"""
+	today = datetime.date.today()
+	someday = today - datetime.timedelta(days=11)
+	someday = someday.strftime("%Y-%m-%d")
+	return someday
+ten_days=get_somedate()
+
+#获取最近10天的数据
+def DATA_recently(x,y,z,q):
+    sql_cid = "select {0}/{1} as {2} from {3} \
+    where stat_date >= ten_days group by stat_date".format(x,y,z,q)
+    CVR_DATA_recently = con_sql(sql_cid)[0][0]
+    return CVR_DATA_recently
+
+#获取固定时间的10天的数据
+def DATA_fixed(x,y,z,q):
+    sql_cid = "select {0}/{1} as {2} from {3} \
+    where stat_date >= " "  and stat_date<" " group by stat_date".format(x,y,z,q)
+    CVR_DATA_fixed = con_sql(sql_cid)[0][0]
+    return CVR_DATA_fixed
+
+#新用户cvr
+x_crv_new=DATA_recently("diary_meigou_newUser","diary_clk_newUser","CVR_new","diary_meigou_crv")
+y_crv_new=DATA_fixed("diary_meigou_newUser","diary_clk_newUser","CVR_new","diary_meigou_crv")
+
+#老用户cvr
+x_crv_old=DATA_recently("diary_meigou_oldUser","diary_clk_oldUser","CVR_old","diary_meigou_crv")
+y_crv_old=DATA_fixed("diary_meigou_oldUser","diary_clk_oldUser","CVR_old","diary_meigou_crv")
+
+#新用户ct-cvr
+x_ctcrv_new=DATA_recently("diary_meigou_newUser","diary_exp_newUser","CT_CVR_new","diary_meigou_crv")
+y_ctcrv_new=DATA_fixed("diary_meigou_newUser","diary_exp_newUser","CT_CVR_new","diary_meigou_crv")
+
+#老用户ct-cvr
+x_ctcrv_old=DATA_recently("diary_meigou_oldUser","diary_exp_oldUser","CT_CVR_old","diary_meigou_crv")
+y_ctcrv_old=DATA_fixed("diary_meigou_oldUser","diary_exp_oldUser","CT_CVR_old","diary_meigou_crv")
+
+#新用户ctr(page_view)
+x_ctr_new=DATA_recently("clk_count_newUser_all","imp_count_newUser_all","ctr_new","bug_Recommendation_strategy_newUser")
+y_ctr_new=DATA_fixed("clk_count_newUser_all","imp_count_newUser_all","ctr_new","bug_Recommendation_strategy_newUser")
+
+#老用户ctr(page_view)
+x_ctr_old=DATA_recently("clk_count_oldUser_all","imp_count_oldUser_all","ctr_old","bug_Recommendation_strategy_temp")
+y_ctr_old=DATA_fixed("clk_count_oldUser_all","imp_count_oldUser_all","ctr_old","bug_Recommendation_strategy_temp")
+
+#新用户ctr(on_click_diary_card)
+x_ctr_new_o=DATA_recently("clk_count_newUser_all_a","imp_count_newUser_all","ctr_new","on_click_diary_card")
+y_ctr_new_o=DATA_fixed("clk_count_newUser_all_a","imp_count_newUser_all","ctr_new","on_click_diary_card")
+
+#老用户ctr(on_click_diary_card)
+x_ctr_old_o=DATA_recently("clk_count_oldUser_all_a","imp_count_oldUser_all","ctr_old","on_click_diary_card")
+y_ctr_old_o=DATA_fixed("clk_count_oldUser_all_a","imp_count_oldUser_all","ctr_old","on_click_diary_card")
+
+
+
+
+def t_test(x,y): #进行t检验
+
+    #策略前的数据，赋值给x,策略后的数据赋值给y,均采用10日内数据
+    x=[2,4,2,3,4,2,3]
+    y=[4,5,6,3,4,5,6]
+
+    #检验数据方差是否齐性
+    a=levene(x,y)
+    p_value=a[1] #结果若p_value>0.05,则认为两组数据方差是相等的，否则两组数据方差是不等的
+
+    if p_value>0.05: #认为数据方差具有齐性，equal_var=ture
+        t_test=ttest_ind(x,y,equal_var=True)
+        t_p_value=t_test[1]
+        if t_p_value>0.05:
+            print("策略前后两组数据无显著性差异，即该指标没有显著提升，p_value:%f" % t_p_value)
+        else:
+            print("策略前后两组数据有显著性差异，即该指标获得显著提升，p_value:%f" % t_p_value)
+    else: #认为数据方差不具有齐性，equal_var=false
+        t_test = ttest_ind(x, y, equal_var=False)
+        t_p_value = t_test[1]
+        if t_p_value > 0.05:
+            print("策略前后两组数据无显著性差异，即该指标没有显著提升，p_value:%f" % t_p_value)
+        else:
+            print("策略前后两组数据有显著性差异，即该指标获得显著提升，p_value:%f" % t_p_value)
+
+###假设检验，判断是否具有显著性
+
+#新用户cvr假设检验
+crv_new_ttest=t_test(x_crv_new,y_crv_new)
+#老用户cvr假设检验
+crv_old_ttest=t_test(x_crv_old,y_crv_old)
+
+#新用户ct_cvr假设检验
+ctcrv_new_ttest=t_test(x_ctcrv_new,y_ctcrv_new)
+#老用户ct_cvr假设检验
+ctcrv_old_ttest=t_test(x_ctcrv_old,y_ctcrv_old)
+
+
+#新用户ctr假设检验
+ctr_new_ttest=t_test(x_ctr_new,y_ctr_new)
+#老用户ctr假设检验
+ctr_old_ttest=t_test(x_ctr_old,y_ctr_old)
+
+##新用户ctr(on_click_diary_card)假设检验
+ctr_new_o_ttest=t_test(x_ctr_new_o,y_ctr_new_o)
+#老用户ctr(on_click_diary_card)假设检验
+ctr_old_o_ttest=t_test(x_ctr_old_o,y_ctr_old_o)
+
+
+###############推荐策略不变的情况下数据假设检验##############
+
+#1 计算每日指标卡方检验
+
+#自动获取5日前的日期
+def get_fivedate():
+	#自动获取10日前的日期,如"2018-07-28"
+	"""
+	:rtype : str
+	"""
+	today = datetime.date.today()
+	someday = today - datetime.timedelta(days=5)
+	someday = someday.strftime("%Y-%m-%d")
+	return someday
+five_days=get_fivedate()
+
+#获取最近5天的数据
+def chi_DATA_recently(x,y,z):
+    sql_cid = "select AVG({0}),AVG({1}) from {2} \
+    where stat_date >= five_days and stat_date<yesterday union all select {0},{1} from {2} where stat_date=yesterday}".format(x,y,z)
+    CVR_DATA_recently = con_sql(sql_cid)[0][0]
+    return CVR_DATA_recently
+
+
+chi_cvr_new=
+chi_cvr_old=
+
+chi_ctcvr_new=
+chi_ctcvr_old=
+
+
+
+def chi_cal(data):